AC godot-plugin
Control Godot Editor via OpenClaw Godot Plugin. Use for Godot game development tasks including scene management, node manipulation, input simulation, debugging, and editor control. Can modify, save, and delete scenes/nodes and capture project metadata and screenshots — destructive operations should be confirmed with the user. Use only on explicit Godot Editor requests like inspecting scenes, creating nodes, taking screenshots, testing gameplay, or controlling the editor, in trusted local projects.
As a process C 57/100 · Has gaps — weak spots: result and completion, consistency, running it twice
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "disableModelInvocation"
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 14 mutating operations with no state check
- 40Consistency. Frontmatter name (godot-plugin) differs from the folder (openclaw-godot-skill)
- 50When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 59 steps
- 100Execution cost. Instruction body is 1829 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 502: enough signal without eating the budget
- +4Structure: 33 headings
- +3Step-by-step instructions: 59 items
- +4Has examples (5 code blocks)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.